From 7cb1b5f5bfcaeb13d0ad4368584bb590274c4f77 Mon Sep 17 00:00:00 2001
From: Rafael Espindola <rafael.espindola@gmail.com>
Date: Fri, 23 Aug 2013 20:39:19 +0000
Subject: [PATCH] Replace more uses of sse41 with sse4.1.

llc using the host cpu features and *waning* on unknown features is probably
not a good thing :-(

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@189144 91177308-0d34-0410-b5e6-96231b3b80d8
---
 test/CodeGen/X86/2008-04-24-pblendw-fold-crash.ll           | 2 +-
 test/CodeGen/X86/2009-02-26-MachineLICMBug.ll               | 4 ++--
 test/CodeGen/X86/2009-04-21-NoReloadImpDef.ll               | 2 +-
 test/CodeGen/X86/2011-09-18-sse2cmp.ll                      | 2 +-
 test/CodeGen/X86/2011-09-21-setcc-bug.ll                    | 2 +-
 test/CodeGen/X86/2011-10-11-srl.ll                          | 2 +-
 test/CodeGen/X86/2011-12-15-vec_shift.ll                    | 4 ++--
 .../CodeGen/X86/2011-12-26-extractelement-duplicate-load.ll | 2 +-
 test/CodeGen/X86/blend-msb.ll                               | 2 +-
 test/CodeGen/X86/crash-nosse.ll                             | 2 +-
 test/CodeGen/X86/floor-soft-float.ll                        | 4 ++--
 test/CodeGen/X86/fold-load-vec.ll                           | 2 +-
 test/CodeGen/X86/movgs.ll                                   | 6 +++---
 test/CodeGen/X86/neg_fp.ll                                  | 2 +-
 test/CodeGen/X86/opt-shuff-tstore.ll                        | 2 +-
 test/CodeGen/X86/pmul.ll                                    | 2 +-
 test/CodeGen/X86/pmulld.ll                                  | 4 ++--
 test/CodeGen/X86/pr10523.ll                                 | 2 +-
 test/CodeGen/X86/pr10524.ll                                 | 2 +-
 test/CodeGen/X86/pr10525.ll                                 | 2 +-
 test/CodeGen/X86/pr10526.ll                                 | 2 +-
 test/CodeGen/X86/pr12312.ll                                 | 2 +-
 test/CodeGen/X86/rounding-ops.ll                            | 2 +-
 test/CodeGen/X86/sse2-blend.ll                              | 2 +-
 test/CodeGen/X86/sse41-blend.ll                             | 2 +-
 test/CodeGen/X86/sse41.ll                                   | 4 ++--
 test/CodeGen/X86/trunc-ext-ld-st.ll                         | 2 +-
 test/CodeGen/X86/vec_extract-sse4.ll                        | 2 +-
 test/CodeGen/X86/vec_fpext.ll                               | 2 +-
 test/CodeGen/X86/vec_insert-8.ll                            | 2 +-
 test/CodeGen/X86/vec_insert-9.ll                            | 2 +-
 test/CodeGen/X86/vec_shift4.ll                              | 2 +-
 test/CodeGen/X86/vec_shuffle-25.ll                          | 2 +-
 test/CodeGen/X86/vec_shuffle-27.ll                          | 2 +-
 test/CodeGen/X86/vec_shuffle-36.ll                          | 2 +-
 test/CodeGen/X86/vec_splat-3.ll                             | 2 +-
 test/CodeGen/X86/vec_ss_load_fold.ll                        | 2 +-
 test/CodeGen/X86/vector-variable-idx2.ll                    | 2 +-
 test/CodeGen/X86/widen_cast-6.ll                            | 2 +-
 39 files changed, 46 insertions(+), 46 deletions(-)

diff --git a/test/CodeGen/X86/2008-04-24-pblendw-fold-crash.ll b/test/CodeGen/X86/2008-04-24-pblendw-fold-crash.ll
index 4eaca17c886..86bce8e977a 100644
--- a/test/CodeGen/X86/2008-04-24-pblendw-fold-crash.ll
+++ b/test/CodeGen/X86/2008-04-24-pblendw-fold-crash.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -mattr=+sse41
+; RUN: llc < %s -mattr=+sse4.1
 ; rdar://5886601
 ; gcc testsuite:  gcc.target/i386/sse4_1-pblendw.c
 target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
diff --git a/test/CodeGen/X86/2009-02-26-MachineLICMBug.ll b/test/CodeGen/X86/2009-02-26-MachineLICMBug.ll
index 8174fbdc9e4..43c23972505 100644
--- a/test/CodeGen/X86/2009-02-26-MachineLICMBug.ll
+++ b/test/CodeGen/X86/2009-02-26-MachineLICMBug.ll
@@ -1,6 +1,6 @@
 ; REQUIRES: asserts
-; RUN: llc < %s -march=x86-64 -mattr=+sse3,+sse41 -mcpu=penryn -stats 2>&1 | grep "4 machine-licm"
-; RUN: llc < %s -march=x86-64 -mattr=+sse3,+sse41 -mcpu=penryn | FileCheck %s
+; RUN: llc < %s -march=x86-64 -mattr=+sse3,+sse4.1 -mcpu=penryn -stats 2>&1 | grep "4 machine-licm"
+; RUN: llc < %s -march=x86-64 -mattr=+sse3,+sse4.1 -mcpu=penryn | FileCheck %s
 ; rdar://6627786
 ; rdar://7792037
 
diff --git a/test/CodeGen/X86/2009-04-21-NoReloadImpDef.ll b/test/CodeGen/X86/2009-04-21-NoReloadImpDef.ll
index 5cb05e8a796..e1930e012dd 100644
--- a/test/CodeGen/X86/2009-04-21-NoReloadImpDef.ll
+++ b/test/CodeGen/X86/2009-04-21-NoReloadImpDef.ll
@@ -1,5 +1,5 @@
 ; RUN: llc -mtriple=i386-apple-darwin10.0 -relocation-model=pic -asm-verbose=false \
-; RUN:     -mcpu=generic -disable-fp-elim -mattr=-sse41,-sse3,+sse2 -post-RA-scheduler=false -regalloc=basic < %s | \
+; RUN:     -mcpu=generic -disable-fp-elim -mattr=-sse4.1,-sse3,+sse2 -post-RA-scheduler=false -regalloc=basic < %s | \
 ; RUN:   FileCheck %s
 ; rdar://6808032
 
diff --git a/test/CodeGen/X86/2011-09-18-sse2cmp.ll b/test/CodeGen/X86/2011-09-18-sse2cmp.ll
index a6f428fdacc..89de648ca96 100644
--- a/test/CodeGen/X86/2011-09-18-sse2cmp.ll
+++ b/test/CodeGen/X86/2011-09-18-sse2cmp.ll
@@ -1,4 +1,4 @@
-;RUN: llc < %s -march=x86 -mcpu=yonah -mattr=+sse2,-sse41 | FileCheck %s
+;RUN: llc < %s -march=x86 -mcpu=yonah -mattr=+sse2,-sse4.1 | FileCheck %s
 
 ;CHECK: @max
 ;CHECK: cmplepd
diff --git a/test/CodeGen/X86/2011-09-21-setcc-bug.ll b/test/CodeGen/X86/2011-09-21-setcc-bug.ll
index 4daf6781495..a67c3f33886 100644
--- a/test/CodeGen/X86/2011-09-21-setcc-bug.ll
+++ b/test/CodeGen/X86/2011-09-21-setcc-bug.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86-64 -mcpu=corei7 -mattr=+sse41
+; RUN: llc < %s -march=x86-64 -mcpu=corei7 -mattr=+sse4.1
 
 ; Make sure we are not crashing on this code.
 
diff --git a/test/CodeGen/X86/2011-10-11-srl.ll b/test/CodeGen/X86/2011-10-11-srl.ll
index 6c6d340fd1a..434f88c14b6 100644
--- a/test/CodeGen/X86/2011-10-11-srl.ll
+++ b/test/CodeGen/X86/2011-10-11-srl.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=-sse41 
+; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=-sse4.1
 
 target triple = "x86_64-unknown-linux-gnu"
 
diff --git a/test/CodeGen/X86/2011-12-15-vec_shift.ll b/test/CodeGen/X86/2011-12-15-vec_shift.ll
index dc3a08bb4da..0183e107460 100644
--- a/test/CodeGen/X86/2011-12-15-vec_shift.ll
+++ b/test/CodeGen/X86/2011-12-15-vec_shift.ll
@@ -1,5 +1,5 @@
-; RUN: llc -march=x86-64 -mattr=+sse41 -mcpu=penryn < %s | FileCheck %s -check-prefix=CHECK-W-SSE4
-; RUN: llc -march=x86-64 -mattr=-sse41 -mcpu=penryn < %s | FileCheck %s -check-prefix=CHECK-WO-SSE4
+; RUN: llc -march=x86-64 -mattr=+sse4.1 -mcpu=penryn < %s | FileCheck %s -check-prefix=CHECK-W-SSE4
+; RUN: llc -march=x86-64 -mattr=-sse4.1 -mcpu=penryn < %s | FileCheck %s -check-prefix=CHECK-WO-SSE4
 ; Test case for r146671
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
 target triple = "x86_64-apple-macosx10.7"
diff --git a/test/CodeGen/X86/2011-12-26-extractelement-duplicate-load.ll b/test/CodeGen/X86/2011-12-26-extractelement-duplicate-load.ll
index 7515e80ef43..f9f037d2688 100644
--- a/test/CodeGen/X86/2011-12-26-extractelement-duplicate-load.ll
+++ b/test/CodeGen/X86/2011-12-26-extractelement-duplicate-load.ll
@@ -1,4 +1,4 @@
-; RUN: llc -march=x86-64 -mattr=-sse42,+sse41 < %s | FileCheck %s
+; RUN: llc -march=x86-64 -mattr=-sse42,+sse4.1 < %s | FileCheck %s
 ; Make sure we don't load from the location pointed to by %p
 ; twice: it has non-obvious performance implications, and
 ; the relevant transformation doesn't know how to update
diff --git a/test/CodeGen/X86/blend-msb.ll b/test/CodeGen/X86/blend-msb.ll
index fa775bd0b91..4f2060f7012 100644
--- a/test/CodeGen/X86/blend-msb.ll
+++ b/test/CodeGen/X86/blend-msb.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7 -mattr=+sse41 | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7 -mattr=+sse4.1 | FileCheck %s
 
 
 ; In this test we check that sign-extend of the mask bit is performed by
diff --git a/test/CodeGen/X86/crash-nosse.ll b/test/CodeGen/X86/crash-nosse.ll
index 7a15a47c6ca..b1e01f94c9e 100644
--- a/test/CodeGen/X86/crash-nosse.ll
+++ b/test/CodeGen/X86/crash-nosse.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -mcpu=corei7 -mattr=-sse2,-sse41 -verify-machineinstrs
+; RUN: llc < %s -mcpu=corei7 -mattr=-sse2,-sse4.1 -verify-machineinstrs
 target triple = "x86_64-unknown-linux-gnu"
 
 ; PR10503
diff --git a/test/CodeGen/X86/floor-soft-float.ll b/test/CodeGen/X86/floor-soft-float.ll
index 8e7ee09004a..5644509a86f 100644
--- a/test/CodeGen/X86/floor-soft-float.ll
+++ b/test/CodeGen/X86/floor-soft-float.ll
@@ -1,5 +1,5 @@
-; RUN: llc < %s -march=x86-64 -mattr=+sse41,-avx -soft-float=0 | FileCheck %s --check-prefix=CHECK-HARD-FLOAT
-; RUN: llc < %s -march=x86-64 -mattr=+sse41,-avx -soft-float=1 | FileCheck %s --check-prefix=CHECK-SOFT-FLOAT
+; RUN: llc < %s -march=x86-64 -mattr=+sse4.1,-avx -soft-float=0 | FileCheck %s --check-prefix=CHECK-HARD-FLOAT
+; RUN: llc < %s -march=x86-64 -mattr=+sse4.1,-avx -soft-float=1 | FileCheck %s --check-prefix=CHECK-SOFT-FLOAT
 
 target triple = "x86_64-unknown-linux-gnu"
 
diff --git a/test/CodeGen/X86/fold-load-vec.ll b/test/CodeGen/X86/fold-load-vec.ll
index 47100be00af..e85d8f78c05 100644
--- a/test/CodeGen/X86/fold-load-vec.ll
+++ b/test/CodeGen/X86/fold-load-vec.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86-64 -mcpu=corei7 -mattr=+sse41 | FileCheck %s
+; RUN: llc < %s -march=x86-64 -mcpu=corei7 -mattr=+sse4.1 | FileCheck %s
 
 ; rdar://12721174
 ; We should not fold movss into pshufd since pshufd expects m128 while movss
diff --git a/test/CodeGen/X86/movgs.ll b/test/CodeGen/X86/movgs.ll
index d3930fadbbf..71b0723c429 100644
--- a/test/CodeGen/X86/movgs.ll
+++ b/test/CodeGen/X86/movgs.ll
@@ -1,6 +1,6 @@
-; RUN: llc < %s -march=x86 -mtriple=i386-linux-gnu -mcpu=penryn -mattr=sse41 | FileCheck %s --check-prefix=X32
-; RUN: llc < %s -mtriple=x86_64-linux -mcpu=penryn -mattr=sse41 | FileCheck %s --check-prefix=X64
-; RUN: llc < %s -mtriple=x86_64-win32 -mcpu=penryn -mattr=sse41 | FileCheck %s --check-prefix=X64
+; RUN: llc < %s -march=x86 -mtriple=i386-linux-gnu -mcpu=penryn -mattr=sse4.1 | FileCheck %s --check-prefix=X32
+; RUN: llc < %s -mtriple=x86_64-linux -mcpu=penryn -mattr=sse4.1 | FileCheck %s --check-prefix=X64
+; RUN: llc < %s -mtriple=x86_64-win32 -mcpu=penryn -mattr=sse4.1 | FileCheck %s --check-prefix=X64
 
 define i32 @test1() nounwind readonly {
 entry:
diff --git a/test/CodeGen/X86/neg_fp.ll b/test/CodeGen/X86/neg_fp.ll
index 57164f2bcaf..efb02f8832e 100644
--- a/test/CodeGen/X86/neg_fp.ll
+++ b/test/CodeGen/X86/neg_fp.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86 -mattr=+sse41 -o %t
+; RUN: llc < %s -march=x86 -mattr=+sse4.1 -o %t
 ; RUN: grep xorps %t | count 1
 
 ; Test that when we don't -enable-unsafe-fp-math, we don't do the optimization
diff --git a/test/CodeGen/X86/opt-shuff-tstore.ll b/test/CodeGen/X86/opt-shuff-tstore.ll
index 3e720844c43..fc43e81bf9b 100644
--- a/test/CodeGen/X86/opt-shuff-tstore.ll
+++ b/test/CodeGen/X86/opt-shuff-tstore.ll
@@ -1,4 +1,4 @@
-; RUN: llc -mcpu=corei7 -mtriple=x86_64-linux < %s  -mattr=+sse2,+sse41 | FileCheck %s
+; RUN: llc -mcpu=corei7 -mtriple=x86_64-linux < %s  -mattr=+sse2,+sse4.1 | FileCheck %s
 
 ; CHECK: func_4_8
 ; A single memory write
diff --git a/test/CodeGen/X86/pmul.ll b/test/CodeGen/X86/pmul.ll
index da4af81959d..169fa33d229 100644
--- a/test/CodeGen/X86/pmul.ll
+++ b/test/CodeGen/X86/pmul.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86 -mattr=sse41 -mcpu=nehalem -stack-alignment=16 > %t
+; RUN: llc < %s -march=x86 -mattr=sse4.1 -mcpu=nehalem -stack-alignment=16 > %t
 ; RUN: grep pmul %t | count 12
 ; RUN: grep mov %t | count 11
 
diff --git a/test/CodeGen/X86/pmulld.ll b/test/CodeGen/X86/pmulld.ll
index 4103eabae5f..3db0f73954d 100644
--- a/test/CodeGen/X86/pmulld.ll
+++ b/test/CodeGen/X86/pmulld.ll
@@ -1,5 +1,5 @@
-; RUN: llc < %s -mtriple=x86_64-linux -mattr=+sse41 -asm-verbose=0 | FileCheck %s
-; RUN: llc < %s -mtriple=x86_64-win32 -mattr=+sse41 -asm-verbose=0 | FileCheck %s -check-prefix=WIN64
+; RUN: llc < %s -mtriple=x86_64-linux -mattr=+sse4.1 -asm-verbose=0 | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-win32 -mattr=+sse4.1 -asm-verbose=0 | FileCheck %s -check-prefix=WIN64
 
 define <4 x i32> @test1(<4 x i32> %A, <4 x i32> %B) nounwind {
 ; CHECK-LABEL: test1:
diff --git a/test/CodeGen/X86/pr10523.ll b/test/CodeGen/X86/pr10523.ll
index 7191d6949c1..0ec22a08e44 100644
--- a/test/CodeGen/X86/pr10523.ll
+++ b/test/CodeGen/X86/pr10523.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86-64 -mattr=+sse2,+sse41
+; RUN: llc < %s -march=x86-64 -mattr=+sse2,+sse4.1
 
 ; No check in a crash test
 
diff --git a/test/CodeGen/X86/pr10524.ll b/test/CodeGen/X86/pr10524.ll
index ed3e7c52805..12bdba9fa59 100644
--- a/test/CodeGen/X86/pr10524.ll
+++ b/test/CodeGen/X86/pr10524.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86-64 -mattr=+sse2,+sse41
+; RUN: llc < %s -march=x86-64 -mattr=+sse2,+sse4.1
 
 ; No check in a crash test
 
diff --git a/test/CodeGen/X86/pr10525.ll b/test/CodeGen/X86/pr10525.ll
index 342c1d63e19..30ce2979e8e 100644
--- a/test/CodeGen/X86/pr10525.ll
+++ b/test/CodeGen/X86/pr10525.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86-64 -mattr=+sse2,+sse41
+; RUN: llc < %s -march=x86-64 -mattr=+sse2,+sse4.1
 
 ; No check in a crash test
 
diff --git a/test/CodeGen/X86/pr10526.ll b/test/CodeGen/X86/pr10526.ll
index 6963fe51589..9fa83ce17b5 100644
--- a/test/CodeGen/X86/pr10526.ll
+++ b/test/CodeGen/X86/pr10526.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86-64 -mattr=+sse2,+sse41
+; RUN: llc < %s -march=x86-64 -mattr=+sse2,+sse4.1
 
 ; No check in a crash test
 
diff --git a/test/CodeGen/X86/pr12312.ll b/test/CodeGen/X86/pr12312.ll
index 087b8d7539e..81aaf91f268 100644
--- a/test/CodeGen/X86/pr12312.ll
+++ b/test/CodeGen/X86/pr12312.ll
@@ -1,4 +1,4 @@
-; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+sse41,-avx < %s | FileCheck %s --check-prefix SSE41
+; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+sse4.1,-avx < %s | FileCheck %s --check-prefix SSE41
 ; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+avx,-avx2 < %s | FileCheck %s --check-prefix AVX
 
 define i32 @veccond128(<4 x i32> %input) {
diff --git a/test/CodeGen/X86/rounding-ops.ll b/test/CodeGen/X86/rounding-ops.ll
index ace31cfeb72..69f4bfb9f47 100644
--- a/test/CodeGen/X86/rounding-ops.ll
+++ b/test/CodeGen/X86/rounding-ops.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -mtriple=x86_64-apple-macosx -mattr=+sse41 | FileCheck -check-prefix=CHECK-SSE %s
+; RUN: llc < %s -mtriple=x86_64-apple-macosx -mattr=+sse4.1 | FileCheck -check-prefix=CHECK-SSE %s
 ; RUN: llc < %s -mtriple=x86_64-apple-macosx -mattr=+avx | FileCheck -check-prefix=CHECK-AVX %s
 
 define float @test1(float %x) nounwind  {
diff --git a/test/CodeGen/X86/sse2-blend.ll b/test/CodeGen/X86/sse2-blend.ll
index 30a0fbe7d6d..1ac983254ea 100644
--- a/test/CodeGen/X86/sse2-blend.ll
+++ b/test/CodeGen/X86/sse2-blend.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86 -mcpu=yonah -mattr=+sse2,-sse41 | FileCheck %s
+; RUN: llc < %s -march=x86 -mcpu=yonah -mattr=+sse2,-sse4.1 | FileCheck %s
 
 ; CHECK: vsel_float
 ; CHECK: pandn
diff --git a/test/CodeGen/X86/sse41-blend.ll b/test/CodeGen/X86/sse41-blend.ll
index bd92d22d5e7..a32f5de30a6 100644
--- a/test/CodeGen/X86/sse41-blend.ll
+++ b/test/CodeGen/X86/sse41-blend.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7 -mattr=+sse41 | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7 -mattr=+sse4.1 | FileCheck %s
 
 ;CHECK-LABEL: vsel_float:
 ;CHECK: blendvps
diff --git a/test/CodeGen/X86/sse41.ll b/test/CodeGen/X86/sse41.ll
index 87b64e58a06..c15e24ccc96 100644
--- a/test/CodeGen/X86/sse41.ll
+++ b/test/CodeGen/X86/sse41.ll
@@ -1,5 +1,5 @@
-; RUN: llc < %s -mtriple=i686-apple-darwin9 -mattr=sse41 -mcpu=penryn | FileCheck %s -check-prefix=X32
-; RUN: llc < %s -mtriple=x86_64-apple-darwin9 -mattr=sse41 -mcpu=penryn | FileCheck %s -check-prefix=X64
+; RUN: llc < %s -mtriple=i686-apple-darwin9 -mattr=sse4.1 -mcpu=penryn | FileCheck %s -check-prefix=X32
+; RUN: llc < %s -mtriple=x86_64-apple-darwin9 -mattr=sse4.1 -mcpu=penryn | FileCheck %s -check-prefix=X64
 
 @g16 = external global i16
 
diff --git a/test/CodeGen/X86/trunc-ext-ld-st.ll b/test/CodeGen/X86/trunc-ext-ld-st.ll
index 408bdc81610..d230f1f7e2c 100644
--- a/test/CodeGen/X86/trunc-ext-ld-st.ll
+++ b/test/CodeGen/X86/trunc-ext-ld-st.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86-64 -mcpu=corei7 -mattr=+sse41 | FileCheck %s
+; RUN: llc < %s -march=x86-64 -mcpu=corei7 -mattr=+sse4.1 | FileCheck %s
 
 ;CHECK-LABEL: load_2_i8:
 ; A single 16-bit load
diff --git a/test/CodeGen/X86/vec_extract-sse4.ll b/test/CodeGen/X86/vec_extract-sse4.ll
index 42d7f27f7d6..3cb519adf4f 100644
--- a/test/CodeGen/X86/vec_extract-sse4.ll
+++ b/test/CodeGen/X86/vec_extract-sse4.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -mcpu=corei7 -march=x86 -mattr=+sse41 -o %t
+; RUN: llc < %s -mcpu=corei7 -march=x86 -mattr=+sse4.1 -o %t
 ; RUN: not grep extractps   %t
 ; RUN: not grep pextrd      %t
 ; RUN: not grep pshufd  %t
diff --git a/test/CodeGen/X86/vec_fpext.ll b/test/CodeGen/X86/vec_fpext.ll
index 863712ff48b..7ec07ae0f95 100644
--- a/test/CodeGen/X86/vec_fpext.ll
+++ b/test/CodeGen/X86/vec_fpext.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86 -mattr=+sse41,-avx | FileCheck %s
+; RUN: llc < %s -march=x86 -mattr=+sse4.1,-avx | FileCheck %s
 ; RUN: llc < %s -march=x86 -mcpu=corei7-avx | FileCheck --check-prefix=AVX %s
 
 ; PR11674
diff --git a/test/CodeGen/X86/vec_insert-8.ll b/test/CodeGen/X86/vec_insert-8.ll
index 650951cc9e5..917832c40ad 100644
--- a/test/CodeGen/X86/vec_insert-8.ll
+++ b/test/CodeGen/X86/vec_insert-8.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86 -mattr=+sse41 -o %t
+; RUN: llc < %s -march=x86 -mattr=+sse4.1 -o %t
 
 ; tests variable insert and extract of a 4 x i32
 
diff --git a/test/CodeGen/X86/vec_insert-9.ll b/test/CodeGen/X86/vec_insert-9.ll
index e5a7ccc5ef9..5f2e676ef1a 100644
--- a/test/CodeGen/X86/vec_insert-9.ll
+++ b/test/CodeGen/X86/vec_insert-9.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86 -mattr=+sse41 > %t
+; RUN: llc < %s -march=x86 -mattr=+sse4.1 > %t
 ; RUN: grep pinsrd %t | count 1
 
 define <4 x i32> @var_insert2(<4 x i32> %x, i32 %val, i32 %idx) nounwind  {
diff --git a/test/CodeGen/X86/vec_shift4.ll b/test/CodeGen/X86/vec_shift4.ll
index 9ef7fbdb0c5..e2fe45cf972 100644
--- a/test/CodeGen/X86/vec_shift4.ll
+++ b/test/CodeGen/X86/vec_shift4.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86 -mattr=+sse41 | FileCheck %s
+; RUN: llc < %s -march=x86 -mattr=+sse4.1 | FileCheck %s
 
 define <2 x i64> @shl1(<4 x i32> %r, <4 x i32> %a) nounwind readnone ssp {
 entry:
diff --git a/test/CodeGen/X86/vec_shuffle-25.ll b/test/CodeGen/X86/vec_shuffle-25.ll
index d9b2388809a..3f42a132ef2 100644
--- a/test/CodeGen/X86/vec_shuffle-25.ll
+++ b/test/CodeGen/X86/vec_shuffle-25.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86 -mattr=sse41 -o %t
+; RUN: llc < %s -march=x86 -mattr=sse4.1 -o %t
 ; RUN: grep unpcklps %t | count 3
 ; RUN: grep unpckhps %t | count 1
  
diff --git a/test/CodeGen/X86/vec_shuffle-27.ll b/test/CodeGen/X86/vec_shuffle-27.ll
index 0aff822850c..8488c2dc5f2 100644
--- a/test/CodeGen/X86/vec_shuffle-27.ll
+++ b/test/CodeGen/X86/vec_shuffle-27.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86 -mcpu=penryn -mattr=sse41 | FileCheck %s
+; RUN: llc < %s -march=x86 -mcpu=penryn -mattr=sse4.1 | FileCheck %s
 
 ; ModuleID = 'vec_shuffle-27.bc'
 target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:32:32"
diff --git a/test/CodeGen/X86/vec_shuffle-36.ll b/test/CodeGen/X86/vec_shuffle-36.ll
index 9a06015745e..f1d0f939e60 100644
--- a/test/CodeGen/X86/vec_shuffle-36.ll
+++ b/test/CodeGen/X86/vec_shuffle-36.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86-64 -mcpu=penryn -mattr=sse41 | FileCheck %s
+; RUN: llc < %s -march=x86-64 -mcpu=penryn -mattr=sse4.1 | FileCheck %s
 
 define <8 x i16> @shuf6(<8 x i16> %T0, <8 x i16> %T1) nounwind readnone {
 ; CHECK: pshufb
diff --git a/test/CodeGen/X86/vec_splat-3.ll b/test/CodeGen/X86/vec_splat-3.ll
index 60e3005edd0..754cbf41867 100644
--- a/test/CodeGen/X86/vec_splat-3.ll
+++ b/test/CodeGen/X86/vec_splat-3.ll
@@ -1,4 +1,4 @@
-; RUN: llc <%s -march=x86 -mcpu=penryn -mattr=sse41 | FileCheck %s
+; RUN: llc <%s -march=x86 -mcpu=penryn -mattr=sse4.1 | FileCheck %s
 
 ; Splat test for v8i16
 define <8 x i16> @shuf_8i16_0(<8 x i16> %T0, <8 x i16> %T1) nounwind readnone {
diff --git a/test/CodeGen/X86/vec_ss_load_fold.ll b/test/CodeGen/X86/vec_ss_load_fold.ll
index 2eb911f1fc1..80f12a2dec2 100644
--- a/test/CodeGen/X86/vec_ss_load_fold.ll
+++ b/test/CodeGen/X86/vec_ss_load_fold.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86 -mattr=+sse,+sse2,+sse41 | FileCheck %s
+; RUN: llc < %s -march=x86 -mattr=+sse,+sse2,+sse4.1 | FileCheck %s
 
 target datalayout = "e-p:32:32"
 target triple = "i686-apple-darwin8.7.2"
diff --git a/test/CodeGen/X86/vector-variable-idx2.ll b/test/CodeGen/X86/vector-variable-idx2.ll
index d47df90e7e6..6e8ae2e42c9 100644
--- a/test/CodeGen/X86/vector-variable-idx2.ll
+++ b/test/CodeGen/X86/vector-variable-idx2.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86-64 -mattr=+sse41
+; RUN: llc < %s -march=x86-64 -mattr=+sse4.1
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
 target triple = "x86_64-apple-darwin11.0.0"
diff --git a/test/CodeGen/X86/widen_cast-6.ll b/test/CodeGen/X86/widen_cast-6.ll
index 39032347c01..7c06ad8ca66 100644
--- a/test/CodeGen/X86/widen_cast-6.ll
+++ b/test/CodeGen/X86/widen_cast-6.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86 -mattr=+sse41 | FileCheck %s
+; RUN: llc < %s -march=x86 -mattr=+sse4.1 | FileCheck %s
 ; CHECK: movd
 
 ; Test bit convert that requires widening in the operand.